Premium
Evaluation of probabilistic prediction systems for a scalar variable
Author(s) -
Candille G.,
Talagrand O.
Publication year - 2005
Publication title -
quarterly journal of the royal meteorological society
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.744
H-Index - 143
eISSN - 1477-870X
pISSN - 0035-9009
DOI - 10.1256/qj.04.71
Subject(s) - probabilistic logic , decomposition , scalar (mathematics) , reliability (semiconductor) , variable (mathematics) , computer science , histogram , mathematics , statistics , econometrics , artificial intelligence , ecology , power (physics) , mathematical analysis , physics , geometry , quantum mechanics , image (mathematics) , biology
A systematic study is performed of a number of scores that can be used for objective validation of probabilistic prediction of scalar variables: Rank Histograms, Discrete and Continuous Ranked Probability Scores (DRPS and CRPS, respectively). The reliability‐resolution‐uncertainty decomposition, defined by Murphy for the DRPS, and extended here to the CRPS, is studied in detail. The decomposition is applied to the results of the Ensemble Prediction Systems of the European Centre for Medium‐range Weather Forecasts and the National Centers for Environmental Prediction. Comparison is made with the decomposition of the CRPS defined by Hersbach. The possibility of determining an accurate reliability‐resolution decomposition of the RPSs is severely limited by the unavoidably (relatively) small number of available realizations of the prediction system. The Hersbach decomposition may be an appropriate compromise between the competing needs for accuracy and practical computability. Copyright © 2005 Royal Meteorological Society.